MohamedAhmedAE
commited on
Commit
•
d256f00
1
Parent(s):
ada5368
Training in progress, step 7400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23743e9690674a1d534f69568011018a38cff6734e126949d34da8a6d936cbe8
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b7b03e4ec1e08ee271094d3bc4edd63ca79ae6d7a5da9e2391644347d04f7a
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d47e244e90ce0cebf2d802c7f97cc46f6230bc0418ded16d90b0ab0fcbef08
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67201e35f3439e7b0671d46d9e3530d28a0b8d3cd07e4d2782d31a603d7c7dac
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -259,6 +259,13 @@
|
|
259 |
"learning_rate": 1.999994358178185e-05,
|
260 |
"loss": 1.5569,
|
261 |
"step": 7200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 200,
|
@@ -266,7 +273,7 @@
|
|
266 |
"num_input_tokens_seen": 0,
|
267 |
"num_train_epochs": 5,
|
268 |
"save_steps": 200,
|
269 |
-
"total_flos": 9.
|
270 |
"train_batch_size": 1,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005503106652437913,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 7400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
259 |
"learning_rate": 1.999994358178185e-05,
|
260 |
"loss": 1.5569,
|
261 |
"step": 7200
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.01,
|
265 |
+
"grad_norm": 1.9615787267684937,
|
266 |
+
"learning_rate": 1.999994039897775e-05,
|
267 |
+
"loss": 1.5864,
|
268 |
+
"step": 7400
|
269 |
}
|
270 |
],
|
271 |
"logging_steps": 200,
|
|
|
273 |
"num_input_tokens_seen": 0,
|
274 |
"num_train_epochs": 5,
|
275 |
"save_steps": 200,
|
276 |
+
"total_flos": 9.719488667027866e+16,
|
277 |
"train_batch_size": 1,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|